VecturaKit: Swift-based on-device vector database with MLX acceleration
rudrank · x · 2026-08-25
VecturaKit is a Swift-based vector database designed for on-device apps, enabling local vector storage and retrieval. It features local storage, indexing, and hybrid search with pluggable embedding providers.
Key Features:
- Multiple Embedder Support: Compatible with OpenAI API, Apple's NaturalLanguage framework, swift-embeddings models, and Apple's MLX framework acceleration (MLXEmbedder).
- On-device Focus: Aims to implement Retrieval-Augmented Generation (RAG) directly on devices.
- CLI Tools: Includes vectura-cli and vectura-oai-cli for local workflow testing.
The project has garnered over 300 stars and is used by Perspective Intelligence 2.5 for AI memories and document parsing.
More from coding & agent
- YC President open-sources 127K-star repo with one-click Claude coding workflow — garrytan · 2026-08-25
- Microsoft Paper Proposes FORCE-Bench and Harness Architecture for Enterprise Agents — solyarisoftware · 2026-08-25
- Cursor Generates and Installs Mouse Wheel App Switcher Plugin Instantly — debreuil · 2026-08-25
- PyMC Labs: Speed Optimization Causes Agents to Skip Self-Checks — twiecki · 2026-08-25
- Rust MCP Memory Server with Provenance and Contradiction Handling — casualboy_10 · 2026-08-25
- Superset launches Design Mode: click elements to chat with any agent — ycombinator · 2026-08-25